Exploratory Data Analysis

Author

JJC

Mortality Rates

Mortality rate by age category

Calculate mortality rate percentage for each age category

Excess Mortality

Method 1: Deaths in excess of the average

year age_cat mort_count pop_count rate_pc avg5yr proj_avg
2010 0-4 327 347000 0.09424 213 NA
2010 5-14 55 610700 0.00901 46 NA
2010 15-24 261 615700 0.04239 170 NA
2010 25-34 449 762800 0.05886 333 NA
2010 35-44 703 681500 0.10315 644 NA
2010 45-54 1425 568300 0.25075 1347 NA

Number of Deaths above Average

Percentage Deaths above Average by Age Group

year age_cat mort_count xs_avg_pc
2020 0-4 180 -15.49
2020 5-14 47 2.17
2020 15-24 136 -20.00
2020 25-34 256 -23.12
2020 35-44 642 -0.31
2020 45-54 1299 -3.56
2020 55-64 2765 -1.46
2020 65-74 5822 6.77
2020 75+ 20618 5.41
2021 0-4 194 -8.92

Method 2A: Difference from 2019 baseline

The baseline level is the 2019 numbers for each age group. Calculate the difference from the baseline, expressed as a percentage.

year age_cat mort_count pop_count rate_pc avg5yr proj_avg base_pc proj_base
2010 0-4 327 347000 0.09424 213 NA 0.06948 NA
2010 5-14 55 610700 0.00901 46 NA 0.00649 NA
2010 15-24 261 615700 0.04239 170 NA 0.02476 NA
2010 25-34 449 762800 0.05886 333 NA 0.04919 NA
2010 35-44 703 681500 0.10315 644 NA 0.08663 NA
2010 45-54 1425 568300 0.25075 1347 NA 0.20768 NA

Death Rate and Baseline Death Rate

Excess Death Rate

Method 2C: Difference from linear trend

Age group“5-14” has low \(r^2\) value (0.42) and so, a linear fit is unwarranted.

Linear Models for Death Rate Progression

Calculate difference between death rate and value predicted by linear models, as a percentage

Fitted and Predicted Values

year age_cat rate_pc fitted_values predicted
2010 0-4 0.09424 0.08841 NA
2010 15-24 0.04239 0.04743 NA
2010 25-34 0.05886 0.06166 NA
2010 35-44 0.10315 0.10716 NA
2010 45-54 0.25075 0.25650 NA
2010 55-64 0.61927 0.63922 NA

Observed Data and Linear Model Comparison

Excess Death Rate

Excess Mortality. Age-group comparison.

Method 1

Method 2A: Difference from 2019 baseline

Method 2C: Difference from Trend

Comparison of Excess Mortality Methods

The age group 5-14 is not given for Method 2C since there is not a linear trend in the observed data. Consequently, applying a linear model is inappropriate in this case

Vaccinations

This analysis uses data from the COVID-19 Vaccine Tracker. This covers all weeks from w53 2020 up to w39 2023. It records the median cumulative uptake (%) of the primary course by age group. It covers the 144 weeks over this time period

The main “Data on COVID-19 vaccination in the EU/EEA” data-set only covers doses administered during the most recent weeks.

Correct Date format.

Warning: package 'ISOweek' was built under R version 4.3.3
Warning: package 'collapse' was built under R version 4.3.3
collapse 2.0.13, see ?`collapse-package` or ?`collapse-documentation`

Attaching package: 'collapse'
The following object is masked from 'package:lubridate':

    is.Date
The following object is masked from 'package:tidyr':

    replace_na
The following object is masked from 'package:stats':

    D
[1] "2015-02-26"

Fit a Logistic Function to the percentage vaccinated.

Appendix

Linear Fit of Death Rate for years 2010 to 2019

Plot Function